Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to a specific hotline or assistance service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    TCA followed by and or semicolon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.60
     OFDb
    -0.54
    getDoctrine
    -0.53
    ########.
    -0.50
    gré
    -0.50
    DebuggerStep
    -0.49
    '])->
    -0.49
    >{@
    -0.48
    ppure
    -0.47
     للمعارف
    -0.46
    POSITIVE LOGITS
    featureID
    0.66
    ThroughAttribute
    0.64
    انجليز
    0.56
     Italij
    0.52
    łbym
    0.50
     grecque
    0.50
     dieß
    0.49
     Nauk
    0.49
     ruft
    0.49
    BeginContext
    0.49
    Act Density 0.002%

    No Known Activations